Building a corpus of spatial relational expressions extracted from web documents.
Jan Oliver WallgrünAlexander KlippelTimothy BaldwinPublished in: GIR (2014)
Keyphrases
- web documents
- web pages
- semi structured
- information extraction
- web search engines
- document classification
- relational data
- vector space model
- relational databases
- web content
- spatial information
- html documents
- spatial data
- textual information
- keywords
- web data
- data model
- natural language
- link structure
- focused crawling
- unstructured documents
- data mining
- natural language processing
- topic specific
- tree structured patterns